[PATCH] D155051: [AMDGPU] Add sanity check that fixes bad shift operation in AMD backend

[Konrad Kusiak via Phabricator via llvm-commits]

konradkusiak97 updated this revision to Diff 540384.
konradkusiak97 added a comment.

included all local changes


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155051/new/

https://reviews.llvm.org/D155051

Files:
  llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp


Index: llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -871,6 +871,9 @@
   unsigned MaxMask = std::max(CI.DMask, Paired.DMask);
   unsigned MinMask = std::min(CI.DMask, Paired.DMask);
 
+  if (!MaxMask)
+    return true;
+
   unsigned AllowedBitsForMin = llvm::countr_zero(MaxMask);
   if ((1u << AllowedBitsForMin) <= MinMask)
     return false;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D155051.540384.patch
Type: text/x-patch
Size: 522 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230714/c2dd6ea6/attachment.bin>